Decoding Machine Learning: Understanding algorithms through math and Python implementation (English Edition) - Tapa blanda

Sinopsis

AI is powering modern industries across different domains, from recommendations to forecasting, making it a must-have skill. As global AI adoption accelerates, it has become necessary for professionals to understand deeply how to utilize machine learning to build more reliable solutions

The book systematically covers foundational to advanced data science concepts through structured programming implementations. It begins with machine learning fundamentals and exploratory data analysis using NumPy and Pandas, then covers the math behind supervised algorithms like linear regression and unsupervised clustering techniques like K-means. You will master ensemble learning architectures like XGBoost, time series forecasting with FBProphet, automated hyperparameter optimization using the Optuna framework, and imbalanced data corrections via SMOTE. The book concludes with a specialized bonus chapter that breaks down the math behind multi-head self-attention mechanisms and fine-tuning strategies within large language model transformer architectures using the Hugging Face ecosystem.

By the end of this book, readers will be able to move confidently from raw data to working models. They will possess practical skills in data preparation, model building, evaluation, and optimization, giving them the confidence to solve complex, data-driven software engineering problems in real-world scenarios.

What you will learn

● Understand core machine learning algorithms from scratch.

● Perform by-hand calculations on small, simple datasets.

● Implement models using Python and popular libraries.

● Explain algorithms in clear, plain English.

● Apply ML concepts to real-world industry scenarios.

● Build confidence for interviews and practical projects.

Who this book is for

Ideal for students, analysts, engineers, and professionals transitioning into AI, this book requires only basic Python programming familiarity. It provides data scientists, educators, and interview candidates with clear mathematical proofs and hands-on workflows to build industry-grade machine learning skills.

Table of Contents

1. Fundamentals of Machine Learning

2. Exploratory Data Analysis

3. Supervised Learning

4. Unsupervised Learning

5. Ensemble Learning

6. Time Series Analysis

7. Model Optimization and Hyperparameter Tuning

8. Handling Imbalanced Datasets

9. Association Rule Mining

10. Neural Networks

11. Fundamentals of Natural Language Processing

12. Recommendation Systems

13. Introduction to Large Language Models

"Sinopsis" puede pertenecer a otra edición de este libro.